most citedUpcycling Models under Domain and Category Shift

1 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation

Tianpei Zou, Sanqing Qu, Zhijun Li +4

3D point cloud segmentation has received significant interest for its growing applications. However, the generalization ability of models suffers in dynamic scenarios due to the di…

cs.CV2024

MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection

Boyang Peng, Sanqing Qu, Yong Wu +5

Deep learning has achieved remarkable progress in various applications, heightening the importance of safeguarding the intellectual property (IP) of well-trained models. It entails…

cs.CV20241 cited

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

Sanqing Qu, Tianpei Zou, Lianghua He +4

Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has…

cs.CV2024

PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds

Haotian Liu, Sanqing Qu, Fan Lu +4

Event cameras can record scene dynamics with high temporal resolution, providing rich scene details for monocular depth estimation (MDE) even at low-level illumination. Therefore,…

cs.CV20231 cited

Modality-Agnostic Debiasing for Single Domain Generalization

Sanqing Qu, Yingwei Pan, Guang Chen +3

Deep neural networks (DNNs) usually fail to generalize well to outside of distribution (OOD) data, especially in the extreme case of single domain generalization (single-DG) that t…

cs.CV20231 cited

Upcycling Models under Domain and Category Shift

Sanqing Qu, Tianpei Zou, Florian Roehrbein +4

Deep neural networks (DNNs) often perform poorly in the presence of domain shift and category shift. How to upcycle DNNs and adapt them to the target task remains an important open…